186 results about "Decision strategy" patented technology

The invention discloses a personalized computer-aided decision-making method and system fusing multi-modal data, and relates to the field of personalized computer-aided decision-making, and the method comprises the steps: mapping multi-source heterogeneous modal data to a unified semantic embedding space, and obtaining a multi-modal unified representation vector set; carrying out three-layer progressive fusion on a feature layer, a situation layer and a decision layer of the multi-modal data to generate a global decision context vector; based on a cross attention mechanism, outputting a fused context sensing personalized vector; based on the behavior cloning model, outputting probability distribution on all decision options; according to the user feedback operation data, generating a user personalized decision strategy and performing dynamic optimization; and generating a structured decision report containing visual traceability information based on the hierarchical fusion process and decision reasoning logic. End-to-end intelligent generation from multi-source heterogeneous data to personalized decisions is realized, and a standardized process is converted into personalized customized decisions.

The invention provides an intelligent e-commerce behavior event decision-making method and system fusing multi-source perception, and the method comprises the steps: obtaining a user behavior data set, a commodity attribute data set and an environment context data set through a preset data collection interface, and carrying out the intention recognition processing of multi-source data; generating an intention feature set containing preliminary intention features and refined intention features, then generating an interactive guidance strategy tree containing node branch weights and strategy execution priorities based on the intention feature set, and performing dynamic path adjustment processing on the interactive guidance strategy tree according to a real-time feedback data set to obtain an optimized strategy tree set; and finally, pushing the optimization strategy tree set to a target interaction interface to activate an interaction guide operation, thereby providing personalized and intelligent interaction guide for the user by fusing multi-source sensing data, deeply understanding the intention of the user and dynamically adjusting a decision strategy, and improving the operation efficiency of an e-commerce platform and the satisfaction of the user.

The invention relates to a multi-competency intelligent scoring method and system, and belongs to the technical field of intelligent evaluation and talent evaluation. The method comprises the following steps: acquiring multi-source response data of a target evaluation object, executing evidence sufficiency and consistency analysis for each competency dimension, generating a judgment state identifier, and constructing a structural description; performing responsibility distribution on the evaluation evidence, mapping the evaluation evidence into a corresponding evidence model and generating a priority constraint relationship; performing time sequence consistency and stability analysis on the evidence model, and constructing a time sequence constraint rule to prohibit unconstrained score backtracking; and carrying out resolution processing on the continuous undetermined dimension, generating a scoring result through a preset risk scoring rule and a conservative determination strategy, and synchronously generating a scoring basis path and confidence information. According to the method, standard management and control of multi-source evidences and accurate constraint of the whole scoring process are realized, the scoring accuracy and traceability are effectively improved, and reliable support is provided for multi-scene talent evaluation decision.

The invention discloses a low-speed unmanned vehicle artificial intelligence decision and performance evaluation system, and belongs to the technical field of low-speed unmanned vehicle scheduling, and the system comprises a generation module which is used for generating a scene novelty index through monitoring the instantaneous offset of an environment parameter; the topology module is used for constructing a dynamic scene topology according to the scene novelty index, and the dynamic scene topology comprises nodes and edge weights generated based on the scene novelty index; the decision-making module is used for converting the edge weight into a decision-making rule according to the dynamic scene topology and generating a decision-making strategy; the performance calculation module is used for tracking the deviation between the vehicle motion parameter and the control instruction during the execution of the decision strategy to calculate a performance disturbance coefficient; and a topology calibration module. The method can effectively adapt to unrecorded edge scenes such as sudden congestion and severe weather superposition, improves the generalization ability of a system to complex scenes exceeding a pre-training range, and reduces decision errors caused by insufficient scene adaptation.

The invention relates to the technical field of energy systems, and discloses an energy system intelligent decision-making method, which comprises the following steps: acquiring four-flow data of an industrial energy system, and constructing a four-flow parameter model based on a production flow topological graph; constructing a multi-agent reinforcement learning environment, taking the four-flow parameter model as a state space of the multi-agent reinforcement learning environment, and determining an action space and a reward function of each agent; performing domain adjustment on the large language model based on the industrial energy system knowledge base; through combination of a multi-agent reinforcement learning model and a large language model, a decision strategy is dynamically adjusted according to real-time data feedback, and decision feasibility verification is performed based on a physical mechanism model. According to the method, the four-flow integrated parameter model is constructed, and a multi-agent reinforcement learning and large language model cooperation mechanism is introduced, so that the problems of data splitting and the like in a traditional energy management system are effectively solved, and the intelligent level of energy system decision making is improved.

The invention discloses a laser operation process control system based on multi-element fusion, and particularly relates to the field of automatic control, which comprises a multi-element perception fusion module, an intelligent decision module, a multi-actuator cooperative control module, a system general control and man-machine interaction module and a self-learning and optimization module, geometric morphology, a temperature field, plasma features and environmental data of an operation area are collected in real time through integration of multiple sensors, a fusion situation information graph is generated through feature extraction and fusion, forward prediction is carried out in combination with a high-fidelity digital twin model, morphology evolution, thermodynamic behaviors and potential defects of a machining area are predicted, and the machining precision is improved. Based on the prediction result, a laser, a movement mechanism and an auxiliary gas unit are synchronously controlled through a high-speed industrial network, collaborative operation, coordination task scheduling, state monitoring and man-machine interaction of multiple actuators are achieved, and model parameters and decision strategies are continuously optimized by comparing actual data with the prediction result.

The invention provides a multi-agent collaborative decision-making system and method for intelligent manufacturing, and relates to the technical field of multi-agent collaboration. Multi-source heterogeneous sensing data are collected and processed, and various sensing feature data are extracted; constructing an edge computing node, deploying a convolutional neural network model at the edge computing node, processing various sensing feature data, and judging abnormal conditions of various sensing data; constructing a digital twinborn model, and when an abnormal condition of an edge computing node is received, integrating various sensing feature data by the digital twinborn model, generating a collaborative decision strategy, and performing collaborative control on multiple groups of agents; and task allocation is performed on a plurality of intelligent monomers in each group of intelligent agents based on an operation cost function, a capability balance condition and a priority, so that real-time perception and dynamic optimization of the manufacturing process are realized.

The invention relates to the technical field of building electromechanical equipment, and discloses an energy efficiency management system for low-carbon and energy-saving operation of building electromechanical equipment, which comprises a random dynamic modeling module, a self-adaptive economic weight module and an energy efficiency management module, the self-adaptive economic weight module is connected with the random dynamic modeling module and the self-adaptive economic weight module and used for calling the probabilistic prediction model according to external macroscopic state information and the attenuation state inside the equipment, and the random prediction control module is connected with the random dynamic modeling module and the self-adaptive economic weight module and used for calling the probabilistic prediction model. And the data processing module is connected with the random dynamic modeling module and the self-adaptive economic weight module and is used for processing the actual operation data of the equipment. According to the method, a double-circulation online learning module is adopted, dynamic adjustment of a prediction model and a decision strategy is achieved through a high-frequency feedback mechanism and a low-frequency feedback mechanism, and the adaptive capacity of the system to environment changes is greatly improved through the method.

The invention relates to the technical field of unmanned scheduling, in particular to a task scheduling method and system based on an unmanned forklift cloud platform. The method comprises the following steps: obtaining a vehicle state flow and an operation instruction flow of an unmanned forklift group, and constructing a vehicle state task set and an operation instruction task set according to a timestamp; generating a scheduling decision feature set based on the vehicle state task set and the operation instruction task set; performing priority mapping on the scheduling decision feature set to generate a first decision instruction set; performing resource adaptation on the scheduling decision feature set to generate a second decision strategy set; therefore, by constructing a data-driven scheduling mechanism based on time sequence alignment, feature extraction, dual-channel decision and closed-loop correction, the problems of data isolation, single feature, decision lag and lack of feedback optimization in the traditional unmanned forklift scheduling process are solved; and the accuracy of task allocation, the stability of system operation and the execution efficiency of the whole operation are improved.

The invention provides a computer network data information identification system, which relates to the technical field of computer network security and data processing and comprises an edge cloud collaborative data acquisition module, a multi-modal feature fusion module, a federated learning dynamic model training module and an intelligent decision and response module. The method has the advantages that the edge cloud collaborative architecture is adopted, data preprocessing and feature extraction are conducted on the network edge, the transmission quantity and delay are reduced, and the real-time performance and the processing efficiency are improved; a self-attention mechanism is used for fusing multi-modal features, so that the recognition accuracy is improved; the data privacy security is protected based on a federated learning framework training model; a reinforcement learning algorithm is introduced to optimize federated learning and decision strategies, and the adaptability and intelligence of the system are enhanced; and response abnormal data can be intelligently dispatched according to an identification result to ensure safe and stable operation of the network.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses a multi-agent communication and decision-making method, device, equipment and medium. The method comprises the following steps: obtaining state information and communication demand information of each agent in a multi-agent system, determining a communication weight based on the information, a dynamic communication topology is constructed in the system, an intelligent agent is used as a graph node, information of neighbor nodes in communication connection with the node is aggregated to generate interactive feature information, a corresponding decision strategy is generated by combining state information of the intelligent agent and the interactive feature information, and joint modeling and optimization of communication and decision are achieved. According to the method, dynamic topology construction is driven through communication weight, interactive feature information is introduced in strategy generation, and a collaborative optimization mechanism is formed by communication and decision, so that redundant communication is reduced, the communication efficiency is improved, and the multi-agent collaborative precision and the task execution effect are enhanced.

The invention relates to the technical field of computer risk control, in particular to a big-data-based collaborative self-optimization method and system for a self-growth risk control system, and the method comprises the steps: obtaining the operation data of the risk control system, so as to construct a state vector; inputting the state vector into a reinforcement learning agent, and selecting one coordination action from a preset coordination action space for output; the coordination action is executed in the risk control system, and a scalar reward value used for evaluating the effect of the coordination action is obtained through calculation; and forming an empirical data tuple by using the state vector, the coordination action, the scalar reward value and a new state of the system after the action is executed, and training the reinforcement learning agent to update a decision strategy of the reinforcement learning agent. According to the risk control system, the rule engine and the model engine in the risk control system can be considered as a unified whole, and respective parameters are dynamically and cooperatively adjusted, so that the overall comprehensive efficiency of the system is maximized, and the self-adaptive capability and the iteration efficiency of the system are improved.

The invention discloses an injection molding production optimization method based on multi-agent cooperation, and the method comprises the following steps: decomposing a plurality of targets in an injection molding production process, and constructing a layered multi-agent structure; collecting data in the injection molding production process in real time, and constructing a global expert behavior track and a local expert behavior track; based on the global target and each local target, obtaining initial parameters of a global reward function and a local reward function; adopting an inverse reinforcement learning method to obtain an optimal global reward function and an optimal local reward function; obtaining an optimal decision strategy of each agent through a hierarchical collaboration mechanism by each hierarchical agent; when detecting that a conflict exists between the targets, dynamically adjusting the reward weight of the reward function by adopting a conflict coordination mechanism; and continuously collecting new expert behavior data, and updating the optimal decision strategy of each agent. According to the invention, a layered multi-agent inverse reinforcement learning method is adopted, and multi-target dynamic collaborative optimization of injection molding production is realized.

The invention provides a space-air-ground integrated ecological monitoring method and system based on multi-source data fusion, and the method comprises the steps: collecting a multi-source heterogeneous data set, carrying out the space-time alignment, multi-scale fusion and dynamic deduction, and generating an ecological change dynamic deduction result; and carrying out ecological monitoring early warning and decision support based on the result. According to the method, cross-platform data is safely cleaned and enhanced through a federated learning framework, and data modal differences are eliminated; deep fusion static feature regression and time sequence trend prediction are carried out by using a double-model architecture, and microenvironment detail changes and long-term ecological trends are synchronously captured; and finally, through a decision strategy model driven by a double-target reward function, quantifying an ecological restoration cost-benefit ratio and a stability gain as an optimal path, forming a'data fusion-dynamic deduction-decision support 'full-link closed loop, improving ecological monitoring space-time continuity, trend prediction accuracy and management decision scientificity, and improving ecological monitoring efficiency. The contradiction that in the prior art, a user can see widely but cannot see finely, and the user can measure finely but does not tend to measure is overcome.

The invention relates to the technical field of pilotless automobiles, in particular to a local obstacle avoidance decision-making method and system based on a dynamic risk map and a real-time game, and the method comprises the steps: obtaining the state information of an automobile and the sensing data of the surrounding environment through a multi-mode sensor; predicting a future trajectory based on the real-time state information of the dynamic obstacle; constructing a rasterized dynamic risk map which takes the vehicle as the center and is updated in real time, and distributing a comprehensive risk value for each grid; the interaction modeling of the self-vehicle and the dynamic obstacle is a non-cooperative game model, the dynamic risk map and the final prediction trajectory of the dynamic obstacle are used as input, the Nash equilibrium of the non-cooperative game model is solved in real time, and the optimal decision strategy of the self-vehicle is output; and converting the optimal decision strategy into a travelable trajectory conforming to vehicle dynamics constraints, and outputting the travelable trajectory to a vehicle control module to execute local obstacle avoidance. The method overcomes the defects of fixed parameters and poor adaptability of a traditional method, and gives consideration to the safety and high efficiency in different scenes.

The invention discloses an intelligent sports event decision-making system based on causal-driven multi-modal fusion and spatio-temporal dynamic reasoning. The system comprises a multi-modal causal data acquisition and preprocessing module; a causal-oriented multi-modal knowledge graph construction and updating module, wherein the causal-oriented multi-modal knowledge graph construction and updating module is provided with a causal structure learning algorithm and an online learning framework; a space-time perception hybrid agent module; the causal constrained dynamic decision optimization module is provided with a deep reinforcement learning algorithm; and the interpretability analysis and visualization module is used for receiving the decision strategy sent by the space-time perception hybrid agent module, generating decision explanation according to the decision strategy and visually presenting the decision explanation. The objective of the invention is to construct an intelligent system capable of providing high-precision, interpretable and adaptive decision support by integrating causal reasoning, multi-modal learning and reinforcement learning, so as to significantly improve scientificity and effectiveness of sports event analysis and decision.

The invention discloses an algae abundance dynamic feature selection method based on multi-agent reinforcement learning, which belongs to the technical field of artificial intelligence and data mining, and comprises the steps of multi-source heterogeneous data acquisition and convergence, time sequence data cleaning and standardization processing, driving factor identification and weight calculation key driving factor set establishment, and dynamic feature selection. Convergence and determination of an optimal feature subset selected by multi-agent reinforcement learning and dynamic features: an MARLN system performs multi-round iteration and interactive learning, and each agent continuously optimizes a decision strategy thereof according to a global reward signal fused with a specification item; according to the method, the problems that a traditional static feature selection method cannot adapt to data changes and neglects interaction among features are solved, the most critical driving factors, namely the features, for algae abundance prediction are automatically recognized from multi-source heterogeneous data through a dynamic feature selection method, and the accuracy of algae abundance prediction is improved. And an optimal feature subset is constructed to improve the precision and robustness of the prediction model.

The invention discloses a competitive evolution multi-task optimization method, system and equipment, and aims to solve the problem that an existing method is difficult to carry out collaborative optimization on fuel cost and gas emission under the condition that power balance and unit capacity constraint conditions are met. The method comprises the following steps: constructing main and auxiliary double-population parallel search; state indexes representing population convergence, diversity and feasibility are calculated in real time; based on the current state, a cooperation mode and evolution operator combined action is adaptively selected through a deep reinforcement learning agent; rewards are calculated according to improvement of the population on cost, emission and constraint satisfaction after action execution; and training the intelligent agent by using the state, the action and the reward, and iteratively optimizing the decision strategy until the Pareto optimal scheduling scheme meeting the constraint is output. According to the method, adaptive intelligent guidance of the evolutionary process is realized, and the optimization quality, the convergence speed and the algorithm robustness of the economic emission scheduling scheme of the power system are remarkably improved.

The invention relates to the technical field of industrial automation, and particularly discloses a fault prevention and diagnosis control system based on a red-mine intelligent mining shield tunneling machine, which is characterized in that time-space synchronous acquisition and fusion of multi-source heterogeneous sensor data are realized through a red-mine operating system, and a multi-dimensional state sequence containing equipment operating parameters and health indexes is constructed; establishing a probability world model based on historical data, predicting state transition probability distribution and quantifying uncertainty; dividing a safety area according to uncertainty, and verifying action safety through multi-step rolling prediction; and iteratively updating a decision strategy by adopting a security constraint strategy optimization algorithm, and dynamically updating model parameters in combination with an online learning mechanism, so that the problems of insufficient data fusion, lagging fault prediction and insufficient exploration action security in the prior art are solved; accurate sensing of the operation state of the shield tunneling machine, early warning of faults and safe autonomous decision making are achieved, and the operation reliability and the maintenance efficiency of equipment are improved.

The invention discloses an intelligent design research and development system based on domestic AI and an implementation method thereof, the system adopts a modular loose coupling architecture, and comprises a front end layer, a middle layer, a core layer, a base layer and a data layer; the front-end layer is a Web front-end interface, and the middle layer is an API gateway layer; the core layer comprises a knowledge graph module, a simulation engine module, a decision center module and a digital twin manager module; the basic layer comprises a system management module, the data layer comprises a multi-layer data storage and communication component, and the method comprises the steps of initializing a system manager, constructing a knowledge graph, executing multi-physics field simulation and evaluating simulation confidence; generating a decision strategy based on reinforcement learning and knowledge graph reasoning; according to the method, digital twin bodies are constructed, virtual-real linkage and real-time data interaction are achieved, domestic AI is comprehensively adopted and comprises a MindSpore framework and an ancient big model, the technology is autonomous and controllable, and the method is suitable for the whole process of power equipment design, inspection and detection and supervision and construction.

The invention discloses an online health monitoring and remote control method and system for hoisting mechanical equipment, and relates to the technical field of industrial equipment health monitoring and intelligent control, and the method comprises the steps: constructing health grade judgment, credibility calculation and abnormal trend intensity analysis results into a real number BPA, carrying out the complex field expansion of the real number BPA, and carrying out the remote monitoring of the health of the hoisting mechanical equipment; obtaining a plurality of evidence sets; calculating the credibility of the plurality of evidences in the plurality of evidence set, and classifying the plurality of evidences, including high-credibility evidences and low-credibility evidences; and performing weight discount correction on the low-credibility evidence, fusing the corrected plurality of evidences by using a plurality of evidence combination rule, and generating a final health evidence value by adopting a conservative decision strategy. Therefore, a stable and credible health assessment conclusion can still be formed when various state assessment results have uncertainty or conflicts, and the conclusion is used as a remote control decision basis, so that the reliability of equipment health state judgment and the safety of a remote control process are improved.

The invention discloses an urban multi-objective collaborative optimization method and system based on deep reinforcement learning, and the method comprises the steps: providing or constructing a building performance agent model, taking a group of urban form design variables as input, and taking a building performance evaluation index as output; constructing a multi-objective collaborative optimization problem into a Markov decision process, and defining the action, state and reward function of an intelligent agent; and training the intelligent agent by adopting a deep reinforcement learning algorithm, and generating an urban form design scheme by applying the optimal decision strategy after training convergence. According to the method, a static and high-dimensional optimization problem is converted into a dynamic decision learning process, and the multi-target and nonlinear complex optimization problem in urban form design is efficiently solved by utilizing the autonomous exploration and optimization capability of deep reinforcement learning; the optimal solution set considering energy efficiency, renewable energy utilization and human settlement environment quality can be quickly generated, and automatic and intelligent decision support is provided for planning and design of sustainable urban communities.

The invention provides a reinforcement learning cross-simulation migration training method, device and equipment for a complex land battle scene, and a storage medium, and the method comprises the steps: carrying out the quick pre-training of a strategy network based on simulation interaction data in a lightweight land battle simulation environment, and obtaining a pre-training strategy network parameter; constructing a cross-simulation state mapping module, an action space alignment module and a reward function consistency constraint module according to the state space dimension, the action space granularity and the reward value distribution difference between the two environments; pre-training strategy network parameters are loaded to a strategy backbone network in the high-fidelity environment, a state mapping module is connected to the input end of the strategy backbone network, an action alignment module is connected to the output end of the strategy backbone network, reward signals are corrected and adapted, a migration strategy network is formed, finally fine tuning training is conducted on the migration strategy network in the high-fidelity land battle simulation environment, and the migration strategy network is obtained. And a target decision strategy suitable for a high-fidelity battlefield environment is obtained.

The invention discloses a cooperative control method for a multi-domain unmanned system. The method comprises the following steps: acquiring an original sensor sequence and a late message set; according to the original sensor sequence, calculating a dominant function and anti-fact regret to obtain a value signal; generating a time delay weight according to the late message set; constructing a space-time source item based on the value signal and the time delay weight; constructing a neural pheromone field by solving partial differential equation dynamics by using space-time source items and pheromone field parameters; under the guidance of the neural pheromone field, sampling to generate a candidate path set; and selecting a cooperative path from the candidate path set for the unmanned system to execute. According to the method, the problems of value characterization and timeliness under asynchronous communication are solved, deep coupling of a decision strategy and a physical model is realized, and the robustness and the adaptive ability of collaborative decision are improved.

The invention provides a multi-model intelligent routing method and system with memory and self-adaptive capabilities in the technical field of artificial intelligence and computer system resource scheduling. The method comprises the following steps: S1, executing an authentication operation based on a user request and extracting a user identifier; s2, performing intention recognition on the user request to extract multi-dimensional request features; s3, retrieving user preference information and a candidate model list related to the user request from a vector database based on the user identifier or the multi-dimensional request feature; s4, acquiring real-time service state information of each model in the candidate model list; s5, based on the multi-dimensional request features, the user preference information and the real-time service state information, a target model is selected from the candidate model list through a mixed decision strategy; and S6, the user request is routed to the target model, and a returned response result is received. The method has the advantages that the model scheduling accuracy, the resource utilization efficiency and the user experience are greatly improved.

The invention discloses a decision strategy rule evaluation method, system and device and a medium, and the method comprises the steps: obtaining a to-be-verified decision strategy rule; executing a decision on the decision strategy rule through at least two different verification modes to obtain a respective decision result set in each verification mode, wherein the at least two different verification modes comprise an offline simulation verification mode, an online shadow verification mode and a real-time small-flow experiment verification mode; performing associated storage and cross comparison analysis on decision results generated by different verification modes based on the unified identifier of the same business case to obtain a cross verification conclusion; and according to the cross validation conclusion and the actual business effect index in the at least one validation mode, evaluating the capability and effect of the decision strategy rule. According to the method, the comprehensiveness, the accuracy and the credibility of decision strategy rule capability and effect evaluation are improved, and the possibility that normal users are accidentally injured or risky users are released after the rules are completely online is effectively reduced.

The invention belongs to the technical field of automated guided vehicles, and particularly relates to a multi-source positioning fusion and navigation correction method and system for an AGV, and the method comprises the steps: carrying out the pose estimation through the bidirectional coupling of extended Kalman filtering and particle filtering, and the estimation uncertainty is fed back to the extended Kalman filter to dynamically adjust the noise parameter. And further introducing sliding window factor graph optimization to carry out back-end smoothing. In the navigation stage, a dynamic decision maker based on deep reinforcement learning is adopted, and optimal control parameters are generated according to real-time positioning, map semantics and historical performance. The system can also enable the filtering model and the decision strategy to adapt to the current environment through periodic online fine tuning. Through innovatively and deeply fusing a classical state estimation method and a leading-edge machine learning method, the positioning precision, the environment understanding capability and the navigation intelligence of the AGV in a complex dynamic scene are remarkably improved.

The invention relates to an electricity-carbon-green evidence fusion multi-market collaborative service equilibrium decision-making method. The method comprises the following steps: step 1, analyzing electricity-carbon-green evidence benefits under a multi-coupling mechanism; step 2, based on the electricity-carbon-green evidence benefit analysis result under the multi-coupling mechanism in the step 1, constructing a system operation optimization model under the multi-coupling mechanism; step 3, training and calibrating the system operation optimization model under the multi-coupling mechanism constructed in the step 2; 4, performing optimization verification on the system operation optimization model under the multi-coupling mechanism after training and calibration in the step 3; and step 5, using the system operation optimization model under the multi-coupling mechanism after optimization verification in the step 4 to output a daily optimal decision strategy to participate in market decision execution. According to the method, collaborative optimization of electric quantity distribution, carbon emission reduction accounting and green certificate configuration can be realized, and the green power consumption accuracy and the multi-market collaborative operation efficiency are improved.

The invention provides a structured modeling and intelligent sorting decision-making method and device for feeding and discharging visual detection data of a metal-based composite material, and is applied to the technical field of data processing. The full-process technical system of data acquisition, threshold setting, processing modeling, strategy making and transmission execution is constructed according to the feeding and discharging sorting requirements of the metal-based composite material. The method comprises the following steps: firstly, collecting visual detection core data and working condition associated data, and setting a multi-dimensional threshold according to sorting precision, defect detection sensitivity and production efficiency; generating a standardized data set through data noise reduction, calibration, alignment and feature extraction, and sorting the standardized data set; determining a sorting decision strategy in combination with characteristics such as material specifications and computing power resources, and matching a sensor acquisition frequency; and after the data set is divided into control batches for ordered transmission, executing parameters are optimized through a multi-modal feature fusion algorithm, equipment and scenes are dynamically adapted, and finally accurate sorting control signals are generated, so that efficient and accurate sorting is realized.

The invention provides a power transaction strategy risk management and control method and system based on reinforcement learning, and the method comprises the following steps: obtaining historical load and weather forecast data of a power transaction subject, inputting the historical load and weather forecast data into a load prediction model to obtain load prediction data, and generating a reference transaction strategy through an optimization algorithm; determining an emergency transaction strategy according to a historical prediction error of the model, and circularly executing the following steps until a decision strategy network of the target agent converges: constructing a current state vector of the target agent in a simulation environment; calculating a strategy fusion coefficient through the decision strategy network; obtaining a final transaction strategy according to the strategy fusion coefficient; and executing the strategy award obtaining signal, and updating adjustable parameters of the strategy network through a reinforcement learning algorithm and the signal. By implementing the technical scheme provided by the invention, prediction deviation can be effectively adapted, the problem of sharp deterioration of strategy performance caused by prediction errors is avoided, and stable and effective risk management and control are realized.